An Algorithm for Building Exterior Facade Corner Point Extraction Based on UAV Images and Point Clouds

The high-precision building exterior facade corner point (BEFCP) is an essential element in topographic and cadastral surveys. However, current extraction methods rely on the interactions of humans with 3D real-scene models produced by unmanned aerial vehicle (UAV) oblique photogrammetry, which have a high workload, low efficiency, poor precision, cannot satisfy requirements automation. dense cloud contains discrete structure information. Still, it challenging to accurately filter out partial characterizing from order achieve BEFCP extraction. BEFCPs are always located plumb line building’s wall. Thus, this paper back-calculated image designed photographic ray corresponding intersection calculation algorithm recover its approximate spatial position successfully extract accurate neighborhood. It then utilized signal-to-noise ratio property as base eliminate noise points and, finally, façade recovering through segmental linear fitting cloud. proposed conducted automated via both planar-to-stereo rough-to-precise strategies, reached 92.06% correctness rate ±4.5 cm mean square location error experiment, was able distinguish under eaves obstruction extreme proximity. suitable for all surveying mapping tasks areas based can effectively improve automation production.